Deep-learning in survival analysis
In this paper, hospitalisation duration is modelled using traditional survival model, machine-learning models and deep-learning models. Machine-learning and deep-learning algorithms typically assume that all event of interest are known at the time of modelling. However, hospitalisation duration i...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/148490 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-148490 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1484902023-02-28T23:12:56Z Deep-learning in survival analysis Ho, Jeff Xiang Liming School of Physical and Mathematical Sciences LMXiang@ntu.edu.sg Science::Mathematics::Statistics In this paper, hospitalisation duration is modelled using traditional survival model, machine-learning models and deep-learning models. Machine-learning and deep-learning algorithms typically assume that all event of interest are known at the time of modelling. However, hospitalisation duration is a time-to-event data with right-censoring (not all events are known at the time of modelling). Hence, specific techniques were employed to deal with this inconsistency. Subsequently, the various models are evaluated using the Concordance-index (C-index). It is a ranking evaluation metrics that can account for censored observation. The empirical results showed that the deep-learning model is best in predicting hospitalisation despite the small dataset. This paper can be further improved by incorporating geo-spatial data in the analysis. Bachelor of Science in Mathematical Sciences and Economics 2021-04-28T02:10:24Z 2021-04-28T02:10:24Z 2021 Final Year Project (FYP) Ho, J. (2021). Deep-learning in survival analysis. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/148490 https://hdl.handle.net/10356/148490 en application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Science::Mathematics::Statistics |
spellingShingle |
Science::Mathematics::Statistics Ho, Jeff Deep-learning in survival analysis |
description |
In this paper, hospitalisation duration is modelled using traditional survival model, machine-learning
models and deep-learning models. Machine-learning and deep-learning algorithms typically assume
that all event of interest are known at the time of modelling. However, hospitalisation duration
is a time-to-event data with right-censoring (not all events are known at the time of modelling).
Hence, specific techniques were employed to deal with this inconsistency. Subsequently, the various
models are evaluated using the Concordance-index (C-index). It is a ranking evaluation metrics that
can account for censored observation. The empirical results showed that the deep-learning model is
best in predicting hospitalisation despite the small dataset. This paper can be further improved by
incorporating geo-spatial data in the analysis. |
author2 |
Xiang Liming |
author_facet |
Xiang Liming Ho, Jeff |
format |
Final Year Project |
author |
Ho, Jeff |
author_sort |
Ho, Jeff |
title |
Deep-learning in survival analysis |
title_short |
Deep-learning in survival analysis |
title_full |
Deep-learning in survival analysis |
title_fullStr |
Deep-learning in survival analysis |
title_full_unstemmed |
Deep-learning in survival analysis |
title_sort |
deep-learning in survival analysis |
publisher |
Nanyang Technological University |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/148490 |
_version_ |
1759854219974672384 |